Intelligent automatic orchestration of machine-learning based processing pipeline

Abstract

Various embodiments of the present invention disclose techniques for orchestrating a complex data processing scheme for an investigative process using a machine-learning based orchestration model that is trained to optimize the use of computing resources based at least in part on a feedback loop. An input data object associated with an investigative process can be selected for investigation; a predictive data analysis sub-routine for processing the input data object can be intelligently selected from a plurality of predictive data analysis sub-routines by the machine-learning based orchestration model; and a processing orchestration action can be initiated based at least in part on an investigative score output by the predictive data analysis sub-routine. The processing orchestration action can include closing the input data object, continuing to process the input data object with additional predictive data analysis sub-routines, or passing the input data object to a predictive entity for further processing.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving, by one or more processors, an input data object profile for a member associated with one or more health insurance payers for a medical claim and an investigative process associated with the one or more health insurance payers;   generating, by the one or more processors and using a machine learning model, an investigative score for the member based at least in part on the input data object profile, wherein the investigative score identifies an investigative potential of the medical claim; and   initiating, by the one or more processors and based at least in part on the investigative score, a processing orchestration action for the member, the processing orchestration action comprising at least one of:
 (i) providing the input data object profile to a predictive data analysis sub-routine of a plurality of predictive data analysis sub-routines, 
 (ii) providing the input data object profile to a processing representative, or 
 (iii) removing the input data object profile from the investigative process. 
   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the predictive data analysis sub-routine comprises at least one of:
 (i) a predictive data verification sub-routine configured to populate the input data object profile with one or more input data object profile parameters,   (ii) a robotic data augmentation sub-routine configured to generate a predicted value for the member, or   (iii) a predictive data augmentation sub-routine configured to generate one or more inferences based at least in part on the input data object profile.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein the input data object profile is provided to the predictive data analysis sub-routine of the plurality of predictive data analysis sub-routines to update the input data object profile with an additional input data object profile parameter, and the computer-implemented method further comprises:
 generating, using the machine learning model, an updated investigative score for the member based at least in part on the input data object profile and the additional input data object profile parameter; and   initiating, based at least in part on the updated investigative score, another processing orchestration action for the member.   
     
     
         4 . The computer-implemented method of  claim 1 , wherein the input data object profile is removed from the investigative process by generating a non-investigative action responsive to the investigative score not achieving a threshold investigative score. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein the input data object profile is provided to the processing representative in response to a determination that the investigative score achieves a threshold investigative score, and the computer-implemented method further comprises receiving an investigative outcome from the processing representative. 
     
     
         6 . The computer-implemented method of  claim 5 , wherein the processing representative is selected using a machine-learning based predictive placement model. 
     
     
         7 . The computer-implemented method of  claim 6 , wherein the machine-learning based predictive placement model is previously trained using a historical optimization data object indicative of an efficiency of processing one or more previously selected input data objects. 
     
     
         8 . The computer-implemented method of  claim 7 , wherein the machine-learning based predictive placement model is retrained based at least in part on the investigative outcome from the processing representative. 
     
     
         9 . The computer-implemented method of  claim 1 , wherein the investigative process comprises a coordination of benefits (COB) process. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein the medical claim comprises an existing medical claim or a prospective medical claim, and the input data object profile is received based at least in part on a creation of the existing medical claim or a probability of the prospective medical claim. 
     
     
         11 . The computer-implemented method of  claim 1 , wherein the input data object profile comprises one or more policy parameters indicative of one or more explanation of benefits associated with the one or more health insurance payers. 
     
     
         12 . A system comprising:
 one or more processors; and   one or more memories storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:   receiving an input data object profile for a member associated with one or more health insurance payers for a medical claim and an investigative process associated with the one or more health insurance payers;   generating, using a machine learning model, an investigative score for the member based at least in part on the input data object profile, wherein the investigative score identifies an investigative potential of the medical claim; and   initiating, based at least in part on the investigative score, a processing orchestration action for the member, the processing orchestration action comprising at least one of:
 (i) providing the input data object profile to a predictive data analysis sub-routine of a plurality of predictive data analysis sub-routines, 
 (ii) providing the input data object profile to a processing representative, or 
 (iii) removing the input data object profile from the investigative process. 
   
     
     
         13 . The system of  claim 12 , wherein the predictive data analysis sub-routine comprises at least one of:
 (i) a predictive data verification sub-routine configured to populate the input data object profile with one or more input data object profile parameters,   (ii) a robotic data augmentation sub-routine configured to generate a predicted value for the member, or   (iii) a predictive data augmentation sub-routine configured to generate one or more inferences based at least in part on the input data object profile.   
     
     
         14 . The system of  claim 13 , wherein the input data object profile is provided to the predictive data analysis sub-routine of the plurality of predictive data analysis sub-routines to update the input data object profile with an additional input data object profile parameter, and the computer-implemented method further comprises:
 generating, using the machine learning model, an updated investigative score for the member based at least in part on the input data object profile and the additional input data object profile parameter; and   initiating, based at least in part on the updated investigative score, another processing orchestration action for the member.   
     
     
         15 . The system of  claim 12 , wherein the input data object profile is removed from the investigative process by generating a non-investigative action responsive to the investigative score not achieving a threshold investigative score. 
     
     
         16 . The system of  claim 12 , wherein the input data object profile is provided to the processing representative in response to a determination that the investigative score achieves a threshold investigative score, and the computer-implemented method further comprises receiving an investigative outcome from the processing representative. 
     
     
         17 . The system of  claim 16 , wherein the processing representative is selected using a machine-learning based predictive placement model. 
     
     
         18 . One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 receiving an input data object profile for a member associated with one or more health insurance payers for a medical claim and an investigative process associated with the one or more health insurance payers;   generating, using a machine learning model, an investigative score for the member based at least in part on the input data object profile, wherein the investigative score identifies an investigative potential of the medical claim; and   initiating, based at least in part on the investigative score, a processing orchestration action for the member, the processing orchestration action comprising at least one of:
 (i) providing the input data object profile to a predictive data analysis sub-routine of a plurality of predictive data analysis sub-routines, 
 (ii) providing the input data object profile to a processing representative, or 
 (iii) removing the input data object profile from the investigative process. 
   
     
     
         19 . The one or more non-transitory computer-readable media of  claim 18 , wherein the investigative process comprises a coordination of benefits (COB) process. 
     
     
         20 . The one or more non-transitory computer-readable media of  claim 18 , wherein the medical claim comprises an existing medical claim or a prospective medical claim, and the input data object profile is received based at least in part on a creation of the existing medical claim or a probability of the prospective medical claim.